arborist/tests/test_query.py
russell@unturf.com fc039555cc
multi-source corpus query: pose a question, the tree pulls related cached docs
aborist/qa/query.py exposes query() — the user-facing RAG flow:

  1. FTS5 search across all shards (chunks_fts can't be UNION'd as a
     view, so each shard's index is queried independently and merged
     by score).
  2. Top-K distinct documents are selected within a max-context-chars
     budget (default 60 KB so a 768-token response fits Hermes-3's
     82 K context window comfortably).
  3. context_root = Merkle root over the sorted source document_roots.
     That's the v9.8 'source' dimension for multi-source answers —
     a verifier can recompute it from the listed source roots.
  4. 8-dim cache_key over (context_root, question_hash, model_profile,
     conversation, governance_policy, schema, canonicalization,
     chunking). Hit returns STRICT immediately; miss calls Hermes and
     persists.

CLI: aborist [--shards-dir DIR] query "<question>"
  Default qa_db is <shards-dir>/qa.db (or ~/.aborist/qa.db). Uses the
  same OpenAICompatibleClient/StubClient as `ask`. --dry-run skips the
  LLM and returns context-only.

Search escape fix: the prior FTS5 escape ANDed every token including
stopwords + punctuation, so "What is anarcho-capitalism?" required
the doc to literally contain "what" + "is" + "anarcho-capitalism?" —
zero hits. New tokenizer drops stopwords + punctuation and ORs the
remaining content tokens; BM25 ranks the multi-token matches highest.

Live demo against the 122k-doc 4-shard cluster:
  Q "What is anarcho-capitalism?"  6.1 s wall miss / 0.45 s cache hit
  Q "Who was George Washington?"   10.3 s wall miss
Both answers cite the source URIs Hermes was given.

57 tests passing (4 new query tests covering search → context →
cache → audit chain).
2026-04-27 11:43:57 -04:00

167 lines
4.9 KiB
Python

"""Multi-source corpus Q&A: search → context → cache → Hermes.
Stub client only — no network. Validates:
- FTS5 finds the right docs across a small corpus
- context_root is deterministic (sorted source roots, then Merkle)
- cache hit on identical question returns same record without calling client
- different question -> different cache_key
"""
from __future__ import annotations
import json
from typing import Iterator
from aborist.document import Document
from aborist.ingest import ingest_source
from aborist.qa import query
from aborist.qa.client import StubClient
from aborist.source import Source
from aborist.store import connect
class FakeSource(Source):
source_type = "test"
def __init__(self, docs: list[Document]):
self.docs = docs
def iter_documents(self) -> Iterator[Document]:
yield from self.docs
def _doc(uri: str, content: str) -> Document:
return Document(uri=uri, content=content, source_type="test", title=uri.rsplit("/", 1)[-1])
# Three docs with distinguishable content so FTS5 can pick winners.
DOCS = [
_doc(
"test://anarchism",
"Anarchism is a political philosophy that opposes the state. " * 12
+ "Mutual aid is central to anarchist theory. " * 8,
),
_doc(
"test://capitalism",
"Capitalism is an economic system based on private ownership. " * 12
+ "Market exchange and capital accumulation drive growth. " * 8,
),
_doc(
"test://anarcho-capitalism",
"Anarcho-capitalism combines anarchism's opposition to the state with capitalism's private property. " * 12
+ "Murray Rothbard developed many of its core ideas. " * 8,
),
]
def test_query_picks_relevant_docs_and_writes_record(tmp_path):
main_db = tmp_path / "corpus.db"
qa_db = tmp_path / "qa.db"
conn = connect(main_db)
try:
ingest_source(conn, FakeSource(DOCS))
finally:
conn.close()
client = StubClient(answer="anarcho-capitalism rests on private property without a state.")
result = query(
question="What is anarcho-capitalism?",
qa_db=qa_db,
chat_client=client,
model_id="test-model",
single_db=main_db,
top_k=3,
)
assert result["status"] == "cache_miss_then_written"
assert result["audit_mode"] == "STRICT"
assert "anarcho-capitalism" in result["answer_text"]
assert len(result["sources"]) >= 1
assert any("anarcho-capitalism" in s["document_uri"] for s in result["sources"])
# context_root is deterministic.
sorted_roots = sorted(s["document_root"] for s in result["sources"])
if len(sorted_roots) == 1:
assert result["context_root"] == sorted_roots[0]
# Repeat call with same question → cache hit, no LLM call.
n_calls_before = len(client.calls)
result2 = query(
question="What is anarcho-capitalism?",
qa_db=qa_db,
chat_client=client,
model_id="test-model",
single_db=main_db,
top_k=3,
)
assert result2["status"] == "cache_hit"
assert result2["cache_key"] == result["cache_key"]
assert len(client.calls) == n_calls_before # no new call
def test_query_different_question_different_cache(tmp_path):
main_db = tmp_path / "corpus.db"
qa_db = tmp_path / "qa.db"
conn = connect(main_db)
try:
ingest_source(conn, FakeSource(DOCS))
finally:
conn.close()
client = StubClient(answer="answer text")
r1 = query(
question="What is anarchism?",
qa_db=qa_db,
chat_client=client,
model_id="m",
single_db=main_db,
)
r2 = query(
question="What is capitalism?",
qa_db=qa_db,
chat_client=client,
model_id="m",
single_db=main_db,
)
assert r1["cache_key"] != r2["cache_key"]
assert len(client.calls) == 2 # both missed cache, both called client
def test_query_no_sources_when_empty_corpus(tmp_path):
main_db = tmp_path / "empty.db"
qa_db = tmp_path / "qa.db"
connect(main_db).close() # creates schema, no docs
result = query(
question="What is anything?",
qa_db=qa_db,
chat_client=StubClient(),
model_id="m",
single_db=main_db,
)
assert result["status"] == "no_sources"
def test_query_persists_audit_event(tmp_path):
main_db = tmp_path / "corpus.db"
qa_db = tmp_path / "qa.db"
conn = connect(main_db)
try:
ingest_source(conn, FakeSource(DOCS))
finally:
conn.close()
query(
question="What is anarchism?",
qa_db=qa_db,
chat_client=StubClient(answer="X"),
model_id="m",
single_db=main_db,
)
# qa.db should now have one providence_query event in its audit chain.
qc = connect(qa_db)
try:
events = qc.execute(
"SELECT event_type FROM audit_events ORDER BY seq"
).fetchall()
finally:
qc.close()
types = [e["event_type"] for e in events]
assert "providence_query" in types